This node combines two PMML document fragments, where one contains a model and the other transformations. In the workflow the process of documenting the transformations and creating the model are separated, so this node can combine them. References to transformed fields in the model are changed to point to the actual derived fields, which are denoted by stars (*) as postfix of the field name. When adding the transformations it is ensured that only fields from the data dictionary are present in the mining schema of the model. When a model is learned on transformed data, it may have transformed fields in the data dictionary and therefore also in the mining schema. Those fields can be safely removed because they are also present in the transformation dictionary of the second input. If a model is learned with a transformed field being the target, the field is removed from the transformation dictionary and a warning is given.
You want to see the source code for this node? Click the following button and we’ll use our super-powers to find it for you.
To use this node in KNIME, install the extension KNIME Modular PMML Nodes from the below update site following our NodePit Product and Node Installation Guide:
A zipped version of the software site can be downloaded here.
Do you have feedback, questions, comments about NodePit, want to support this platform, or want your own nodes or workflows listed here as well? Do you think, the search results could be improved or something is missing? Then please get in touch! Alternatively, you can send us an email to firstname.lastname@example.org, follow @NodePit on Twitter, or chat on Gitter!
Please note that this is only about NodePit. We do not provide general support for KNIME — please use the KNIME forums instead.